ClawHub
Back to skill

Security audit

多平台视频图文发布助手

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed local browser-assisted social publishing helper, with broad trigger wording but no hidden credential access, persistence, or automatic posting shown in the artifacts.

Install only if you want an agent to assist with publishing from social accounts already logged in on your browser. Confirm the exact platform, account, file, title, and final publish action before proceeding; testing with a non-primary account is prudent.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger list ends with a catch-all phrase for similar multi-platform publishing requests, which can cause the skill to activate on loosely related user intents. Because this skill can drive browser automation against logged-in social media accounts, overbroad activation increases the chance of unintended posting actions or the skill being invoked in contexts the user did not explicitly mean.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal